Repository navigation
Conversation
…s /review blocker proof (GST-1088 lane C, candidate) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…T-1088 lane C) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
|
Merging to
After your PR is submitted to the merge queue, this comment will be automatically updated with its status. If the PR fails, failure details will also be posted here |
…ned reviewer briefs keep their no-loss-tested bytes (GST-1088 lane C) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
… forced-CRITICAL findings, marker override, Step 3.5 anchors, E2E section bracket, pins lowered to measured) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…adout error codes (Step 14.5 audit) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…h the ledger and with an empty one, on every host Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…-1088-lane-c Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> # Conflicts: # test/fixtures/skill-md-size-allowlist.json # test/helpers/carve-guards.ts
…al agent_dispatch marker in the contract resolver), cap comments cite gate rev 2, pins at the combined measurement Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…r (match alone gates it), shared-preamble cut check, changelog at post-#3909 sizes, pins at measured (review 56,716, ratio 1.2979) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…g as /investigate Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…docs2-7370b4ba) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
4 of 9 tasks
6 tasks done
Contributor
|
Closing: held since 11-03 for the GST-1089 before/after measurement, and its thread is archived. The branch is kept. If the measurement supports these cuts, the work is rebuilt on current main. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Candidate: do not merge until the GST-1089 measurement passes and GStack Minder confirms the crew behavior change. This is the after pin for GST-1088. It changes /review's prompts, so the crew no-loss rule applies (2026-10-30). It never boards a train on its own.
What changed
/review Step 4: every CRITICAL finding now needs a floor reason and proof, or it is reported as INFORMATIONAL. The marker paragraph pins the
Dispatchinglines that evals count./investigate drops its learnings search and the investigation learnings log: 21,242 to 17,838 always-loaded bytes against v1.94.24.0.
/investigate loads about 3.4 KB less and /review about 3.3 KB less, and every blocking /review finding must now prove itself.
modules/cuts.jsonis a new cut ledger. Each entry is apart:<skill>/<name>module id thatgstack-modules listshows with statuscut. A cut applies in every loadout,fullincluded, and on every host, but only to its own skill.modules/loadouts.jsonis unchanged, so no other skill loses anything. One cut, /review's repo-ownership section, is a preamble piece;preambleSections()drops it for /review alone. The rest are deleted from the two templates.fails a test,breaks production,loses data or secrets, or one of the Sideways sweep's forced-CRITICAL classes) and proof: a repro with its output, a failing test, or a citedfile:linewith its consequence. /review verifies a forwarded finding (specialist, QA, adversarial or bot) and appends both itself, so the pinned reviewer briefs don't change. A CRITICAL nobody proves is INFORMATIONAL at Step 5, whatever itsBlocks:line. The rule is in the Step 4 critical pass and in the review-only branch of the pre-emit verification gate (scripts/resolvers/confidence.ts).Dispatching N specialists:line, small diffs included, and the native adversarial pass printsDispatching adversarial pass: nativebefore its Agent call. These are for eval counting. Theadversarial-passcontract item stays gated bymatchalone, exactly as on main. This PR adds nomarker:to the frontmatter and doesn't touch the contract resolver.review/sections/review-army.md,review/sections/adversarial.mdand their resolvers are unchanged, so the pinned reviewer briefs and /ship keep their bytes.test/cut-ledger.test.tsfails when a cut piece comes back in its skill, its sections or the shared preamble file on any host, when a pinned size moves, when a cut names a skill other than /investigate or /review, or when review-only text shows up in any other skill.Why
Opus 5.5 read these skills in full and still skipped their required steps (Run D, gstack-evals#140). The forced full /review caught 67.2% of blocking bugs but raised 2.71 false blockers per PR per pass (gstack-evals#120). The cuts take out text that nothing measured shows is doing work. The blocker-proof rule targets the false-blocker rate. GST-1089 (GEVA-214) decides whether either one keeps.
Blast radius
Durable scope test.
test/cut-ledger.test.tsrenders every host twice, once from the tree and once from a copy whosemodules/cuts.jsonhas no cuts, and asserts that every file outside the investigate and review trees is byte-identical. As a negative control, a cut added to the office-hours preamble failed it on all 12 non-Claude hosts. A second test checks that no preamble cut comes back through the sharedsections/preamble.mdon any host. As its negative control, appending## Repo Ownershiptoreview/sections/preamble.mdfailed it.Pins (all lowered to measured at 9386a27, no headroom):
modules/cuts.json:72-73: investigate 17838, review 56716.test/helpers/carve-guards.ts:493: /reviewmaxSkeletonBytes60,014 to 56,716.:496:maxSizeRatio1.3283 to 1.2979 (140,849 / 108,523 = 1.29788).:898: /investigateminUnionBytes55,000 to 54,778.test/fixtures/skill-md-size-allowlist.json:9-55: nine*/gstack-reviewpins lowered to measured. The values are agy 101,780, codex 100,964, copilot 101,398, cursor 119,875, factory 122,253, gemini 101,225, kiro 119,713, opencode 120,462 and slate 119,794.carve-guards.ts:164), module size 800 and PART_MAX 24,576.Sibling trial merges (CREW rule 25 with the 2026-11-03 addendum), at 9386a27:
test/fixtures/skill-md-size-allowlist.jsonconflicts, anddocs/skills.mdmerges cleanly. The resolution keeps this PR's review and investigate pins and v1.94.29.0 R56: everything in gstack earns its place (principle, evidence gates, inventory) #3837's other pins. On the merged tree,bun run typecheckexits 0 and 49 focused test files ran 1,766 tests with no failures. Sizes are unchanged: review 56,716, investigate 17,838, ratio 1.29788.test/helpers/carve-guards.tsand the allowlist conflict, because both PRs re-pin the same lines. The resolution takes this PR's side and re-pins up to the combined measurement. That gives review 56,772 and investigate 17,894 (both +56 bytes), ratio 1.2984 (140,905 / 108,523 = 1.29839) and every*/gstack-reviewallowlist pin +24. On the merged tree,bun run typecheckexits 0,gen:skill-docsis fresh, and 44 focused test files ran 1,668 tests with no failures. Whichever PR lands second raises those pins, and that raise needs Garry via GStack Minder.docs/troubleshooting.mdmerged cleanly with main. Its diff against v1.94.24.0 is only this PR's LOADOUTS_INVALID and MODULE_SPEC_INVALID cut wording.Approvals
Documentation
Status: updated. One factual paragraph added to docs/skills.md; no blockers.
Scope. Ship candidate
laneC-docs2-7370b4baoncapy/gst-1088-lane-c, base 1ccab0d to head 8cd564a: 28 committed files, with no staged, unstaged or untracked files. Docs inventory: 136 candidate docs, plus authored templates found withgit ls-files(849 doc-type files). Banned terms: none (the repo keeps no list).Documentation health
liststatus column and the Cuts section matchmodules/cuts.json,scripts/modules.ts,test/cut-ledger.test.tsand the livegstack-modules listoutput (7partrows, status cut).validateLoadoutsandselectModules.scripts/judge-controls.tscut to## Step 3.5.lib/skill-contract.tshonors an optionalagent_dispatchmarker).Coverage debt
markeras an optionalagent_dispatchfield. The gen-time parser inscripts/resolvers/contract-done-means.tsrejects that key, and /review's adversarial item declares onlymatch.Diagram drift: none. No ASCII or Mermaid entity in the reviewed docs names a cut piece.
Behavior changes
Removed from the generated skills, on every host and in every loadout:
part:investigate/learnings-search## Prior Learnings: a learnings search plus the cross-project AskUserQuestionpart:investigate/capture-learnings## Capture Learningsat the end of the runpart:investigate/investigation-loggstack-learnings-logcall withtype: "investigation"part:review/learnings-search## Prior Learningsin Step 3.6part:review/capture-learnings## Capture Learningsafter the final reportpart:review/repo-ownership## Repo Ownership — See Something, Say Somethingpart:review/queue-statusgstack-next-version)gstack-skill-end). It writes the timeline'scompletedevent with the real outcome and duration, and it drains artifacts sync (bin/gstack-skill-end:59-69).skill_routingandskill_contractsare untouched.Always-loaded bytes (the Claude
SKILL.md, frontmatter included):Tests changed, with reasons:
test/cut-ledger.test.ts(new): the ledger ratchet, the durable scope test (every host, ledger vs empty ledger, byte-identical outside investigate and review) and the shared-preamble check.test/learnings-callers-unavailable.test.ts,test/learnings.test.tsandtest/gen-skill-docs.test.ts(LEARNINGS_SEARCH, LEARNINGS_LOG, operational type, Factory paths): these follow the ledger. A cut skill must render no learnings block, and the resolver-content checks read the first uncut sample skill instead. No assertion changes for any other skill.test/review-workflow-clarity.test.ts: section-boundary tokens move from## Step 3.4:,{{LEARNINGS_SEARCH}}and{{LEARNINGS_LOG}}to the next heading, because those markers were cut.test/fixtures/workflow-required-steps.json: drops /review's pinned## Step 3.4step.test/pr-dependencies.test.ts: the "a template invokes a bin" example moves from /review to /ship, because /review no longer callsgstack-next-version.test/exercised-map.test.ts: addsscripts/cut-ledger.tsto REVIEWED_SUPERSET, because the preamble imports it.test/setup-claude-code-migration.test.ts: the generator fixture also copiesmodules/, because rendering now readsmodules/cuts.json.test/review-fix-range.test.ts: its Step 3 slice ended at the cut## Step 3.4:. It now ends at## Step 3.5:and asserts that both anchors exist in order.scripts/judge-controls.tsanddocs/evals/judge-controls-2026-10.md: the review judge's defect bundle cut Step 3 up to## Step 3.4, which madecut()throw. The end anchor is now## Step 3.5, which removes the same text.test/helpers/carve-guards.tsandtest/fixtures/skill-md-size-allowlist.json: the pins listed under Blast radius.Pre-Landing Review
REVIEW_LOOP: passes=1 blocking_found=0 deferred=0 noted=1 fixed=5 scope=frozen fix_checks=1
Pass 1 ran at full depth on 27052ff, with the money class from
scripts/cut-ledger.ts. Its readers were a batched specialist, the Red Team, the native adversarial pass, the outside voice (GPT-6.1 Sol) and the targeted reader, and nothing reached the blocking floor. The fix round, 8cd564a, did three things. It dropped the adversarialmarker:, because adversarial-native#1 showed the checker passing on the marker plus any later Agent call. It also added the shared-preamble check and restated the changelog against v1.94.24.0. One fix-check read it and raised one informational note: /review's saving rounds to 3.3 KB, not 3.2. That is fixed in e25b935. After the docs audit commit, the targeted reader read the final head, 9386a27, and found nothing.Review notes
scripts/resolvers/confidence.ts:52still says "log the corrected pattern as a learning" even though /review's Capture Learnings section is cut. The shared preamble's learnings logger still gives the command.lib/skill-contract.ts:370-377(lane A's checker) counts anagent_dispatchmarker plus any later Agent call as met. No skill declares a marker now, but the checker behavior stands.Eval Results
Not run in this PR.
bun run eval:selectfalls back to every gate case and judge, becausescripts/resolvers/preamble.tsis a shared input. That is far over the lane's $10 paid cap. This PR merges only after the GST-1089 no-loss replay.Test plan
gstack-ship-release finish: 1,577 tests, 0 fail, 2 skip. It covers the carve and size guards, the cut ledger, the skill fixture, review clarity and fix range, gen-skill-docs, review packets, the module-size ratchet, learnings, skill descriptions, the exercised map, bun entry isolation, the spawnsync tripwire, pr-dependencies, the setup migration, workflow required steps, skill-contract, the stop hook, skill-route, skill-validation and review-depth.bun run typecheckexits 0, andgen:skill-docs --dry-runis fresh.